^{1}

^{*}

^{1}

^{2}

The power grid is a fusion of technologies in energy systems, and how to adjust and control the output power of each generator to balance the load of the grid is a crucial issue. As a platform, the smart grid is for the convenience of the implementation of adaptive control generators using advanced technologies. In this paper, we are introducing a new approach, the Central Lower Configuration Table, which optimizes dispatch of the generating capacity in a smart grid power system. The dispatch strategy of each generator in the grid is presented in the configuration table, and the scenario consists of two-level agents. A central agent optimizes dispatch calculation to get the configuration table, and a lower agent controls generators according to the tasks of the central level and the work states during generation. The central level is major optimization and adjustment. We used machine learning to predict the power load and address the best optimize cost function to deal with a different control strategy. We designed the items of the cost function, such as operations, maintenances and the effects on the environment. Then, according to the total cost, we got a new second-rank-sort table. As a result, we can resolve generator’s task based on the table, which can also be updated on-line based on the environmental situation. The signs of the driving generator’s controller include active power and system’s
*f*. The lower control level agent carries out the generator control to track
*f* along with the best optimized cost function. Our approach makes optimized dispatch algorithm more convenient to realize, and the numerical simulation indicates the strategy of machine learning forecast of optimized power dispatch is effective.

With the fast society innovation speed, the higher demand for power industry is required, such as higher quality, better stability, lower harmonics and inter-harmonics, etc. Therefore, it has become inexorable trend that utilizing modern science technology improves power system quality, and smart grid will and must be the future electric system [

There are two kinds of thoughts to implement control; one is adjusting the side of demand via electricity price. In recent years, researchers have got some results. I. Dusparic et al., in [

and allows both users initiated jobs and EMS initiated jobs, more flexible requests. K. Khezeli et al. issued risk sensitive learning and electrical pricing for demand response [

The other way is controlling the side of supply (include generators, optimize adjustment system). Many researchers focus on the side of generation [

In adjustment and electrical power system optimization aspect, some methods are published [

Related works in recent years some researches were published [

The main contributions of this research are summarized as follows:

■ The costs of analysis power grid not only contains economics but also generator’s emission, so we use a total cost (a society cost) as our optimized goal. With society development, the emission effect becomes an attentive event, hence multi-optimal goal needs to be considered, and in economic aspect, operation and maintenance are major considered. The weights of consisting total cost can be change to obtain a different optimal goal.

■ Use hierarchical strategy to optimize our goal, the central level implements active power dispatch in the best way according to configuration table, the lower control level convert P_{dispatch} to control value u to perform P out, at the same time calculate the generator’s next the capacity of output according to the local weather and generator work state, then feedback the result P_{f} to the central level to update configuration table.

■ Embed load forecast technology into the central level, strategy implement power dispatch based on forecast result suit to the P_{f}.

■ Dispatch protocol is a form convenient to show, save and update on time.

This paper is organized as follows: Section 2 explains the problem and gives some preliminaries about machine learning technology. Section 3 states the idea’s detail of this paper, and constructs optimized dispatch system model. Numerical simulations are given in Section 4. Some results and conclusions remarked are described in Section 5. The last but not the least is some acknowledgements.

For the further analysis, the following contents are needed.

Introduce SVM’s regression basic theory start with linear regression. When parameter W satisfied KKT the best linear regression hyperplane:

f ( X , W ) = W T X + b = ∑ i = 1 l ( α i − α i * ) X i T X + b . (1)

where W , b are parameters of space, Lagrange multipliers α i and α i * .

If nonlinear regression:

G = [ G 11 ⋯ G 1 l ⋮ ⋱ ⋮ G l 1 ⋯ G l l ] (2)

where G i j = K ( X i , X j ) , and the weight vector of the kernel v 0 = α − α * , therefore, regression hyperplane rewrite as follow:

f ( X , W ) = G V 0 + b (3)

We use SVM’s regression theory to forecast electrical power load.

Generating technology including all kinds of methods, for example, traditional way hydropower plant, coal-fired generator, gas fired generator, and new energy such as Nuclear, wind power, photovoltaic generation, bioenergy power, tidal power station, and so on. Here we consider mainly most common generations technology, shown in

Operation costs are different for all kinds of generating technology. According to [

We present such a goal function as below Equation (4).

p i = f i ( e i , c i , r i ) (4)

Technology | Operation cost [ | O & M [ | GHG emissions [ |
---|---|---|---|

Coal Fired Power | 0.02 - 0.04 | 43 | 973 |

Gas Fired Power | 0.04 - 0.1 | 20 | 450 |

Wind Power | <0.01 | 46 | 23 |

Nuclear Power | 0.02 - 0.05 | 198 | 31.7 |

Photovoltaic Solar Power | <0.01 | 25 | 84.8 |

Hydro Power | <0.01 | 53 | 36.9 |

where p i denotes dispatch power of the generator i, f i denotes the function on generator, e i , c i , r i denotes environment situations, generation type class and output ratio of the generator i respectively. The parameter c i will get different consider based on our optimized purpose, e i is designed for environment situation, for example if its night time and daytime we should give different considering to solar energy. Here, we mainly aim to the total cost including many contents like

Minimize : S c o s t = ∑ i = 1 l S c o s t ( P g ( i ) ) . Subject to : ∑ i = 1 l P g ( i ) − ∑ P d = 0 , P G ∈ [ 0 , P g m a x ] , P D ∈ [ 0 , P d m a x ] . (5)

where P G denotes the total generations of all running generators in the power grid, P D describes the total demand of the power grid. P g m a x , P d m a x denote the maximal generation and demand respectively. S c o s t is the goal cost include minimize total cost 6 and track the best output power of the generator.

Here we normalize the cost of different main power technology to convenient to analysis, the normal method shown in (6).

C n ( i ) = c n ( i ) / ∑ i = 1 6 c n ( i ) , n = 1 , 2 , 3 , T o t a l c o s t = ∑ n = 1 3 λ n C n . (6)

where, c n ( i ) means the cost of the n item of i type generator, C n ( i ) denotes the normal cost of c n ( i ) . T o t a l c o s t is the total cost of three type cost of a generator described in

We get the bar chart of costs about generators according to

We get the power hourly load data of BG, and divide original power data into training data and testing data. Firstly, we use three days data for training and testing, then we use the head of eighteen data of a day as training data, the rest data of the day for predicting.

In order to realize power dispatch in the future smart grid, we propose a hierarchy optimize protocol is shown in

In this strategy, the most important thing is to decide controlling which generators in a grid. Our scenario is shown in

Notes: the result of this algorithm is a dispatch generating configuration table according to minimize total cost, and consider Equation (4) v i and c i individually, c i is the first place and v i behind of it. We realize c i through the first factor sort based on total cost of the generator, realize v i via the second factor according to active power from bigger to smaller.

The scheme of the strategy we use the process as following to show you. First of all, we introduced the upper strategy is how to create dispatch power data. Then we introduced the lower control agent how to do it after getting the dispatch task.

➢ Step 1: Data prepare. The parameters of generator were shown 1 normalized as

➢ Step 2: Design a form for output strategy and initialize it. This form is ranked by two parameters, that is generator’s cost and generator’s output rating individually. When first time running system, we must let the work state column of the form equal zero.

➢ Step 3: Load forecast. We predict next some time load in the power grid use machine learning method by last period time running load data in the grid. then we got a predicted value of the next load P_{f}.

Technology | normalized operation cost | normalized O & M | normalized GHG emissions |
---|---|---|---|

Coal Fired Power | 0.18 | 0.11 | 0.61 |

Gas Fired Power | 0.41 | 0.05 | 0.28 |

Wind Power | <0.06 | 0.12 | 0.01 |

Nuclear Power | 0.24 | 0.51 | 0.02 |

Photovoltaic Solar Power | 0.06 | 0.06 | 0.05 |

Hydro Power | 0.06 | 0.14 | 0.02 |

➢ Step 4: Based on P_{f} implement dispatch strategy. Firstly we need to get the generators’ cost from the form, then choose generators to assign active power which fits our protocol rules, about its details as shown in algorithm

➢ Step 5: Ahead of step 4, we have got the dispatch table, and know the work state of all generators in a grid in the next work’s situation, that’s the column workstate in the form. This step we need to do some jobs on converting and control in lower agent, convert the dispatch active P to control generator’s variable u to perform active output. The method is that when grid frequency fluctuate range extra power grid allowance trigger controller output u, about some this rule details refer from

Load forecast schematic described in

where,

Suppose BG power grid has a consisted energy as shown in

get the dispatch table as shown in

Simulation results show that optimized algorithm of dispatch is convenient to realize by second rank sorting, and all of the worked generators are working on rated power, that’s means it working on the highest efficient except only the last one.

Id | Class | Power_E (kw) | Workstate | Distance (km) | Total_cost |
---|---|---|---|---|---|

G1 | wind | 500,000 | 0 | 30 | 0.19 |

G2 | water | 700,000 | 0 | 150 | 0.22 |

G3 | pv | 50,000 | 0 | 10 | 0.17 |

G4 | gas | 5000 | 0 | 10 | 0.74 |

G5 | nuclear | 550,000 | 0 | 200 | 0.77 |

G6 | coal | 60,000 | 0 | 15 | 0.22 |

G7 | water | 33,000 | 0 | 50 | 0.22 |

G8 | coal | 60,000 | 0 | 15 | 0.9 |

G9 | water | 50,000 | 0 | 80 | 0.22 |

G10 | water | 1000 | 0 | 50 | 0.22 |
---|---|---|---|---|---|

G11 | wind | 10000 | 0 | 30 | 0.19 |

G12 | coal | 800,000 | 0 | 60 | 0.9 |

G13 | coal | 30,000 | 0 | 30 | 0.9 |

G14 | pv | 30,000 | 0 | 5 | 0.17 |

G15 | gas | 20,000 | 0 | 10 | 0.74 |

G16 | wind | 500,000 | 0 | 30 | 0.19 |

G17 | water | 700,000 | 0 | 150 | 0.22 |

G18 | pv | 50,000 | 0 | 10 | 0.17 |

G19 | gas | 5000 | 0 | 10 | 0.74 |

G20 | nuclear | 550,000 | 0 | 200 | 0.77 |

G21 | coal | 100,000 | 0 | 20 | 0.9 |

G22 | water | 33,000 | 0 | 50 | 0.22 |

G23 | coal | 60,000 | 0 | 15 | 0.9 |

G24 | water | 50,000 | 0 | 80 | 0.22 |

G25 | water | 1000 | 0 | 50 | 0.22 |

G26 | wind | 10,000 | 0 | 30 | 0.19 |

G27 | coal | 800,000 | 0 | 60 | 0.9 |

G28 | coal | 30,000 | 0 | 30 | 0.9 |

G29 | pv | 30,000 | 0 | 5 | 0.17 |

G30 | gas | 20,000 | 0 | 10 | 0.74 |

No. | Id | Class | Power_E (kw) | Workstate | Distance (km) | Total_cost |
---|---|---|---|---|---|---|

2 | G3 | PV | 50,000 | 100 | 10 | 0.17 |

17 | G18 | PV | 50,000 | 100 | 10 | 0.17 |

13 | G14 | PV | 30,000 | 100 | 5 | 0.17 |

28 | G29 | PV | 30,000 | 100 | 5 | 0.17 |

0 | G1 | Wind | 500,000 | 77 | 30 | 0.19 |

No. | Id | Class | Power_E (kw) | Workstate | Distance (km) | Total_cost |
---|---|---|---|---|---|---|

2 | G3 | PV | 50,000 | 100 | 10 | 0.17 |

17 | G18 | PV | 50,000 | 100 | 10 | 0.17 |

13 | G14 | PV | 30,000 | 100 | 5 | 0.17 |

28 | G29 | PV | 30,000 | 100 | 5 | 0.17 |

0 | G1 | Wind | 500,000 | 100 | 30 | 0.19 |

10 | G11 | Wind | 10,000 | 100 | 30 | 0.19 |

25 | G26 | Wind | 10,000 | 100 | 30 | 0.19 |

8 | G9 | Water | 50,000 | 100 | 80 | 0.22 |

23 | G24 | Water | 50,000 | 100 | 80 | 0.22 |

Notes: Hypothesis we have got a power grid energy consists of

In this paper, we address a new approach to realize power configuration in the smart grid, and make dispatch strategy reflect in a configuration table based on operation cost and environment effect cost. This method consists of two-level parts, dispatch configuration central and lower control agent of the generator. In the central, we mainly did these things: dispatching optimized calculation, converting it into configuration table, and updating it. The lower control agent aims to realize control generators according to central and feedback generators’ new best working power based on the situation. In the central level, use machine learning to predict power load, and address the best-optimized cost function to adapt to the different control strategies. Then we do dispatch based on the table, which can be updated online based on environmental conditions. The signs of triggering controller are both active power and system f. The lower control agent carries out the generator to track f along with the best optimized cost function. In the numerical simulation, we used BG grid load as forecast data to train machining learning model, gave two predicted load data at random, and took them as the cases. We obtained good simulation results, right dispatch configuration table, and the table has been updated online. So, this scenario makes optimized dispatch algorithm more convenient to realize and effective.

In the future work, we will keep on optimizing strategy research, consider more situations when designing cost function, and try our best to get a real large-scale power grid, which includes more generated technology.

This research was financially supported by the National Science Foundation (No. 41804148), the Education Department of Sichuan Province Foundation (No. 18ZB0273) and Leshan Science and Technology Bureau Foundation (No. 15NZD100), China. The authors would like to thank them. The power data used in this research comes from Open Power System Data: http://www.open-power-system-data.org/, so we also thank Open Power System Data group open data.

The authors declare no conflicts of interest regarding the publication of this paper.

Jiang, Q., Hu, D. and He, D.Y. (2020) Forecasting-Based Adaptive Optimized Dispatch in Smart Grid Online. International Journal of Modern Nonlinear Theory and Application, 9, 1-18. https://doi.org/10.4236/ijmnta.2020.91001